Usage artificial intelligence for diagnosing diseases is becoming more common. First of all, algorithms are often used that can track X-rays or MRIs looking for abnormalities that indicate a disorder. He mammary cancer It was one of the most studied of its kind. But now artificial intelligence has been improved to such an extent that it can predict its appearance even four years earlier.
At least that’s how he explained CNN Dr. Larry Norton, Medical Director of the Lauder Breast Center at Memorial Sloan-Kettering Cancer Center. According to him, thanks to the artificial intelligence algorithm developed by Massachusetts Institute of Technology (MIT), spots may be found that may become breast cancer in the future.
This does not mean that artificial intelligence will replace radiologists. Not even that he can 100% guarantee that these spots will develop into breast cancer. However, this may be very useful tool so radiologists decide in advance what preventive measures patients can take.
Artificial intelligence will prevent breast cancer
Like any other artificial intelligence algorithm, this one was training on mammography images healthy patients who either developed breast cancer or never did. Thus, the machine is able to capture common factors in all cases and detect spots that disappear over time. they can turn into cancer.
As Dr. Norton explained, it can be expected up to four years. But this does not eliminate the role of the radiologist. It is this person who should subsequently analyze the mammogram and make a diagnosis. If the possibility of cancer is definitively confirmed, the patient can make decisions based on her risk.
If you also have high-risk mutated genes, you can choose to run mastectomy. However, it may be sufficient to run regular tests such as MRIto control possible swelling.
In an interview, the head physician explains that in this way other more invasive tests can be avoidedsuch as biopsies that are done regularly can be very annoying.
AI will not take jobs from radiologists
Radiologists studying mammograms are known to miss one in eight breast cancer diagnoses. There is nothing strange in this, because they do not cease to be people, and sometimes it is very difficult to see the tumor in the pictures.
For this reason, artificial intelligence is perceived as just another tool. However, these algorithms can also generate false positives, so the radiologist will always have the final say. So, diagnostics will be improvedor, with a subsequent benefit to patients who can take action sooner. This is not about stealing work or replacing someone, but about adding to the list of tools that these professionals already have. Any help will always be welcome.
Source: Hiper Textual
